Prepare
Collecting Data from the Web with Python If you like
PASCAL VOC
. ├── VOCdevkit │ └── VOC2018 │ ├── Annotations ├── ImageSets │ │ └── Main // name of *.jpg without “.jpg” ├── JPEGImages // *.jpg
Annotation
LabelImg is a graphical image annotation tool
Example : XML
000
000000.jpg
/home/water/Machine_Learning/Peppa_Pig/train/000/000000.jpg
Unknown
410
256
3
0
Peppa
Unspecified
0
0
64
87
166
226
Peppa
Unspecified
0
0
290
77
333
131
Generate Labels for VOC
Darknet wants a .txt file for each image with a line for each ground truth object in the image that looks like:
voc_label.py
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets=[(‘2018’, ‘train’), (‘2018’, ‘val’)]
classes = [“Peppa”]
def convert(size, box):
dw = 1./size[0]
dh = 1./size[1]
x = (box[0] + box[1])/2.0
y = (box[2] + box[3])/2.0
w = box[1] - box[0]
h = box[3] - box[2]
x = x*dw
w = w*dw
y = y*dh
h = h*dh
return (x,y,w,h)
def convert_annotation(year, image_id):
in_file = open(‘VOCdevkit/VOC%s/Annotations/%s.xml’%(year, image_id))
out_file = open(‘VOCdevkit/VOC%s/labels/%s.txt’%(year, image_id), ‘w’)
tree=ET.parse(in_file)
root = tree.getroot()
size = root.find(‘size’)
w = int(size.find(‘width’).text)
h = int(size.find(‘height’).text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
continue
cls\_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
bb = convert((w,h), b)
out\_file.write(str(cls\_id) + " " + " ".join(\[str(a) for a in bb\]) + '\\n')
wd = getcwd()
for year, image_set in sets:
if not os.path.exists(‘VOCdevkit/VOC%s/labels/‘%(year)):
os.makedirs(‘VOCdevkit/VOC%s/labels/‘%(year))
image_ids = open(‘VOCdevkit/VOC%s/ImageSets/Main/%s.txt’%(year, image_set)).read().strip().split()
list_file = open(‘%s_%s.txt’%(year, image_set), ‘w’)
for image_id in image_ids:
list_file.write(‘%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n’%(wd, year, image_id))
convert_annotation(year, image_id)
list_file.close()
peppa.data
classes= 1
train = /home/d/Downloads/Peppa_VOC/2018_train.txt
valid = /home/d/Downloads/Peppa_VOC/2018_val.txt
names = data/peppa.names
backup = backup
yolov3-voc-peppa.cfg
[net]
Testing
batch=1
subdivisions=1
Training
batch=64
subdivisions=2
width=416
height=416
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1
learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1
[convolutional]
batch_normalize=1
filters=16
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=1
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky
###########
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=18
activation=linear
[yolo]
mask = 3,4,5
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
classes=1
num=6
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
[route]
layers = -4
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = -1, 8
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=18
activation=linear
[yolo]
mask = 0,1,2
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
classes=1
num=6
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
Train
./darknet detector train cfg/peppa.data cfg/yolov3-voc-peppa.cfg darknet53.conv.74
Test
Reference
@article{yolov3,
title={YOLOv3: An Incremental Improvement},
author={Redmon, Joseph and Farhadi, Ali},
journal = {arXiv},
year={2018}
}